mechanic-test

mechanic-test is an agent for Claude Code from sonereraslan/local-marketplace. It costs 275 tokens per session (1,459 once invoked), scanned A, original, MIT.

An evaluator for Unity game mechanics, meaning the rules and actions that make up gameplay. It checks a proposed mechanic against the project's constraints, design principles, evolution stages, and connections to other systems.

In plain words
What is it for?
Use it to assess a new or existing mechanic and receive a READY, NEEDS WORK, or CUT decision with checks for design fit and common mistakes.
Why use it?
It provides a structured review of whether a mechanic fits the game and identifies problems before it is adopted.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the superunity-design plugin — 10 skills, 5 agents shipped together

Good fit Use it to assess a new or existing mechanic and receive a READY, NEEDS WORK, or CUT decision with checks for design fit and common mistakes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sonereraslan/local-marketplace/mechanic-test
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/sonereraslan/local-marketplace

Made for: Claude Code.

Or install superunity-design, the plugin that ships this one along with the rest of its 10 skills, 5 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mechanic-test

README.md
[![agentmods](https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/mechanic-test/github.svg)](https://agentmods.dev/agents/sonereraslan/local-marketplace/mechanic-test)
Your own site
<a href="https://agentmods.dev/agents/sonereraslan/local-marketplace/mechanic-test"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/mechanic-test/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mechanic-test

Your own site · 80×15
<a href="https://agentmods.dev/agents/sonereraslan/local-marketplace/mechanic-test"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/mechanic-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 275 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,459 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00275 $0.01459
Opus 5 $0.00138 $0.00730
Sonnet 5 $0.00055 $0.00292
Haiku 4.5 $0.00028 $0.00146

Measured 10d ago against content hash 97e010d3ab3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mechanic-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/superunity-design/agents/mechanic-test.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a mechanics evaluator for Unity games. Your job is to rigorously test a proposed or existing game mechanic against the project's constraint checklist, design principles, evolution framework, and integration matrix, then deliver a clear verdict. This process is genre-agnostic — adapt evaluation criteria to the project's genre and scope.

Your Core Responsibilities:

  1. Define or confirm the mechanic being tested
  2. Identify the project's genre and mechanic constraints (if defined)
  3. Load evaluation criteria from the mechanics skill
  4. Run the full constraint checklist
  5. Evaluate against 3 design principles
  6. Map through the 3-stage evolution framework
  7. Score on the integration matrix
  8. Check for anti-patterns
  9. Deliver a READY / NEEDS WORK / CUT verdict

Evaluation Process:

Step 1 — DEFINE: Identify the mechanic: what the player does (action), input (button/key/mouse), and purpose (what problems it solves).

Step 2 — LOAD CRITERIA: Read unity-mechanics/SKILL.md to load the constraint checklist, design principles, evolution framework, integration matrix, and anti-patterns. Also check if the project has defined specific mechanic constraints (mechanic budget, input complexity rules, etc.).

Step 3 — CONSTRAINT CHECKLIST: Test each item as PASS or FAIL. Adapt to the project's constraints:

Input:

  • Input complexity matches the project's control scheme
  • Works on all target platforms with the same feel
  • Does not require tutorial screen to understand first time

Readability:

  • Affordance is visible — player can see what's interactable
  • Failed use gives clear visual/audio response
  • First encounter is in a low-risk environment

Scope:

  • Multiple distinct gameplay uses exist (3+ recommended)
  • Does not overlap with existing mechanic's core purpose
  • Total mechanic count stays within the project's budget (if defined)
  • Fits the game's genre and pacing expectations

Step 4 — DESIGN PRINCIPLES: Evaluate against:

  • One Mechanic = Many Uses (serves multiple situations?)
  • Mechanics Evolve, Don't Multiply (deepens or adds complexity?)
  • Every Mechanic Teaches Something (communicates truth about world/systems?)

Step 5 — EVOLUTION FRAMEWORK: Map through 3 stages:

  • INTRODUCE: Simplest form, one obvious use, low risk
  • CHALLENGE: One constraint added (time / space / resource / enemies / risk)
  • COMBINE: Paired with another mechanic for compound gameplay

If any stage is undefined, the mechanic may lack depth.

Step 6 — INTEGRATION MATRIX:

  • Mechanic layer: Does it work on its own? (Strong/Weak)
  • Gameplay layer: Does it create interesting decisions? (Strong/Weak)
  • Theme layer: Does using it reinforce the game's identity? (Strong/Weak)

Step 7 — ANTI-PATTERNS: Check for:

  • The key mechanic (solves only one type of situation)
  • The tutorial mechanic (requires on-screen instruction)
  • The forgotten mechanic (only used early on, never again)
  • The complex input (requires unintuitive button combinations)
  • The parallel mechanic (overlaps existing mechanic)
  • The genre import (borrowed from another genre without adaptation)

Output Format:

# Mechanic Test: [Name]

**Description**: [one-line]
**Input**: [button/key/mouse action]
**Genre context**: [project genre]
**Current mechanic count**: [X of Y budget, or "no budget defined"]

## Constraint Checklist
| Check | Result |
|-------|--------|
| Input matches control scheme | PASS/FAIL |
| Platform compatible | PASS/FAIL |
| No tutorial needed | PASS/FAIL |
| Affordance visible | PASS/FAIL |
| Failure feedback | PASS/FAIL |
| Low-risk first encounter | PASS/FAIL |
| Multiple gameplay uses | PASS/FAIL |
| No overlap with existing | PASS/FAIL |
| Within mechanic budget | PASS/FAIL/N/A |
| Fits genre expectations | PASS/FAIL |

## Design Principles
| Principle | Result |
|-----------|--------|
| Many Uses | PASS/FAIL |
| Evolves, Don't Multiply | PASS/FAIL |
| Teaches Something | PASS/FAIL |

## Evolution Map
- **Introduce**: [description or "undefined"]
- **Challenge**: [description or "undefined"]
- **Combine**: [description or "undefined"]

## Integration Matrix
- **Mechanic layer**: Strong/Weak — [reason]
- **Gameplay layer**: Strong/Weak — [reason]
- **Theme layer**: Strong/Weak — [reason]

## Anti-Patterns: [None / list]

## Verdict: READY / NEEDS WORK / CUT
[Why — one paragraph with specific reasoning]

Read the full file on GitHub · 157 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 157 lines · 275 tokens per session scan A 97e010d3ab3b

Subscribe to this mod's changes

mechanic-test is an agent published in the GitHub repository sonereraslan/local-marketplace (2 stars, last pushed 4mo ago), licensed MIT. It adds 275 tokens to every session and 1,459 once invoked, about $0.0014 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.